Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58844
    Prev
    Next
    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Excerpt
    -0.09
     actually
    -0.08
     perpendicular
    -0.08
     obrigatório
    -0.08
     cunn
    -0.08
     narrated
    -0.08
     każdy
    -0.08
    BOOST
    -0.08
     sugest
    -0.08
     INVENT
    -0.07
    POSITIVE LOGITS
     Mehrheit
    0.10
     majority
    0.10
     dominance
    0.10
     faction
    0.10
     victory
    0.09
     побед
    0.09
     victories
    0.09
     manipulation
    0.09
     Win
    0.09
     alliances
    0.09
    Activations Density 0.043%

    No Known Activations